?

Log in

Graphical Models of Probability
Bayesian Networks, Decision Networks, and Probabilistic Relational Models
Recent Entries 
21st-Jan-2009 01:26 pm - Tutorials?
I'm looking for any tutorial documents on BNJ.  I'm trying to build on OS X , so I downloaded the SRC files, but cannot seem to get any further. 
13th-Jun-2006 07:09 pm - A Joke
Q: Why did the Bayesian reasoner cross the road?

A: You need more information to answer that question.
13th-Jun-2006 04:52 pm - BNJ tutorials or manuals
Hey Everone,
I'm a student at Michigan State University doing an internship for the summer. I downloaded BNJ from bnj.sourceforge.net, but the user tutorials aren't posted yet. Does anyone know where I could find some basic instruction on how to use the program?
Thanks in advance,
Rob
29th-Dec-2005 04:10 am - Using GP to build Bayes Net
recently I was asked by a friend on if it would be possible to build/evolve Bayes Net with Genetic Programming. I don't know how to answer it as I only know the very basic of how Bayesnet works ... What do you think ?

One of the first questions that I raise is why needs to use GP to build BN. Can a BN model be at such a difficulty level that it requires a heuristic approach such as GP ?
2nd-Jun-2005 12:20 am - traveling salesman with a twist
kid
So here is a problem.

Imagine you have a list of cities that a salesman wants to visit, each on a particual date or range of dates.
You know, Moscow: June 1-3; Tokio: June 17; New York: June 19-25, etc. Well, technically instead of ranges I have probability distributions over the dates when the "conference" of interest for the traveling salesman occurs...

Also here is a list of transit station which the salesman can travel through: Paris, Singapour, Washington, whatever.

All these Cities can be I guess arranged in a simple graph bu what is important not every city is connected to another one, there is a network of "railroads" connecting those (I know, there is no railroad between Tokio and New York, but let it be :)). Of course those railroads have lengths (cost functions, and those are probabilistic) associated with those.

What the salesman needs is an optimal path that would make it possible to make o all those conferences or meetings by the dates specified (and i does not matter, what transition he is taking, but it should make sence in terms of lengths of the paths between those cities, that is, he should be choosing the paths hat would make "perfect timing" for him.

I am pretty sure this is a well known "classic" problem, but what is the "classic" name for the problem?
I would really appreciate if you could help me categorize the problem so that I would know where to start my search for an appropriate algorithm.

Thanks guys!

UPDATE: It appears that Hidden Markov Models (which could be actually implemented as a special case of Bayes Nets) provide a nice framework to deal with my problem.
28th-May-2005 11:14 pm - Gene Regulatory Networks
Blasted Earthlings
I just needed to find out if there is any member here who is into Bayesian modeling of gene regulatory networks and cellular signaling pathways. I'd love to chat up with anyone working on the same thing.

-S
28th-May-2005 12:29 pm(no subject)
Hi, I am new to this forum. I am a mathematical sciences major planning on taking elective statistics for the major, and hoping to get a few relevant questions answered:

Is Java a good programming language for statisticians? Numerical analysts? I noticed that this community is predicated on it.

EXTRA CREDIT-- I had a discrete mathematics exam, and I was able to probably earn partial credit on everything except this question: You have six coin tosses, and it's given that three heads and three tails are resultant. How many possible orders are there?
24th-May-2005 11:32 am(no subject)
Hello everyone,

I'm taking the math exam to reenter the college world, as my ACT scores no longer hold any value, since they're 11 years old. I'm reading a refresher math text, but I've come across something that for the life of me, I cannot recall ever doing and cannot grasp. I'm a very logical person, so if someone can explain "Permutations" to me in a way that is utilitarian and not just a jumble of formulas, please help. Also, Pascal's triangle is baffling, and as it applies to this as well ...
31st-Mar-2005 11:54 am - Baysian network learning
Hi everyone, I need some help.

I am currently doing a project that uses BNJ for its "brains" and requires the Bayes net to be able to "learn". However, the current version of BNJ does not have any learning classes implemented.
Hence, I was wondering if there are any plans to implement these classes in the near future, like for version 2. If not, any advice on how I can allow the bayes net to "learn" would be greatly appreciated.
Thanks.
12th-Jan-2005 12:37 pm - surveys
Hi folks, I need your help!
Have anybody ever created surveys? Have anybody ever created web surveys? If yes – you are my target audience and I need to research you :) if you don’t mind. My student assignment is to find a way to improve usability of an app for creating web surveys.( http://www.surveymonkey.com/ and such)
Do you develop questionnaire yourself or use a questionnaire that has already been developed and standardized by someone else? Do you work with some app that helps you create a survey? Do you interact with the app yourself or you ask somebody to do it for you? What kind of instructions do you give her? What could be the criteria of a success interaction with such a web app? In what context and under what circumstances would the interaction occur?
Thanks!
This page was loaded May 25th 2017, 2:32 pm GMT.